In this paper, we propose a new approach for 3D face verification based on tensor representation. Face challenges, such as illumination, expression and pose, are modeled as a multilinear algebra problem where facial images are represented as high order tensors. Particularly, to account for head pose variations, several pose scans are generated from a single depth image using Euler transformation. Multi-bloc local phase quantization (MB-LPQ) histogram features are extracted from depth face images and arranged as a third order tensor. The dimensionality of the tensor is reduced based on the higher-order singular value decomposition (HOSVD). HOSVD projects the input tensor in a new subspace in which the dimension of each tensor mode is reduced. To discriminate faces of different persons, we utilize the Enhanced Fisher Model (EFM). Experimental evaluations on CASIA-3D database, which contains large head pose variations, demonstrate the effectiveness of the proposed approach. A verification rate of 98.60% is obtained.
Chouchane Ammar, Ouamane Abdelmalik, Boutellaa Elhocine, Belahcene Mebarka, Bourennane Salah
A1 Journal article – refereed
Place of publication:
Chouchane, A., Ouamane, A., Boutellaa, E. et al. Multimed Tools Appl (2018) 77: 20697. https://doi.org/10.1007/s11042-017-5478-z
Read the publication here: